EMNLP 2021 Papers

Recently, disentanglement based on a generative adversarial network or a variational autoencoder has significantly advanced the performance of diverse applications in CV and NLP domains. Nevertheless, those models still work on coarse levels in the disentanglement of closely related properties, such as syntax and semantics in human languages. This paper introduces a deep decomposable model based on VAE to disentangle syntax and semantics by using total correlation penalties on KL divergences. Notably, we decompose the KL divergence term of the original VAE so that the generated latent variables can be separated in a more clear-cut and interpretable way. Experiments on benchmark datasets show that our proposed model can significantly improve the disentanglement quality between syntactic and semantic representations for semantic similarity tasks and syntactic similarity tasks.

Coordination is a phenomenon of language that conjoins two or more terms or phrases using a coordinating conjunction. Although coordination has been explored extensively in the linguistics literature, the rules and constraints that govern its structure are still largely elusive and widely debated amongst linguists. This paper presents a study of two-termed unlike coordinations in particular, where the two conjuncts of the coordination phrase form valid constituents but have distinct categories. We conducted a syntactic analysis of the phrasal categories that can be conjoined in such unlike coordinations through a computational corpus-based approach, utilizing the Corpus of Contemporary American English (COCA) as the main data source, as well as the Penn Treebank (PTB). The results show that the two conjuncts within unlike coordinations display different properties based on their position, supporting an antisymmetric view of the structure of coordination. This research provides new data and perspectives through the use of statistical techniques that can help shape future theories and models of coordination.

We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditional Generative Matching models (CGM), optimized within a Variational Autoencoder framework to address challenges arising from multilingual RS. CGM does so with expressive message conditional priors, mixture densities to enhance multilingual data representation, latent alignment for language discrimination, and effective variational optimization techniques for training multilingual RS. The enhancements result in performance that exceed competitive baselines in relevance (ROUGE score) by more than 10% on average, and 16%for low resource languages. CGM also shows remarkable improvements in diversity (80%) illustrating its expressiveness in representation of multi-lingual data.

In this paper we study pejorative language, an under-explored topic in computational linguistics. Unlike existing models of offensive language and hate speech, pejorative language manifests itself primarily at the lexical level, and describes a word that is used with a negative connotation, making it different from offensive language or other more studied categories. Pejorativity is also context-dependent: the same word can be used with or without pejorative connotations, thus pejorativity detection is essentially a problem similar to word sense disambiguation. We leverage online dictionaries to build a multilingual lexicon of pejorative terms for English, Spanish, Italian, and Romanian. We additionally release a dataset of tweets annotated for pejorative use. Based on these resources, we present an analysis of the usage and occurrence of pejorative words in social media, and present an attempt to automatically disambiguate pejorative usage in our dataset.

Coreference Resolution is an important NLP task and most state-of-the-art methods rely on word embeddings for word representation. However, one issue that has been largely overlooked in literature is that of comparing the performance of different embeddings across and within families. Therefore, we frame our study in the context of Event and Entity Coreference Resolution (EvCR & EnCR), and address two questions : 1) Is there a trade-off between performance (predictive and run-time) and embedding size? 2) How do the embeddings’ performance compare within and across families? Our experiments reveal several interesting findings. First, we observe diminishing returns in performance with respect to embedding size. E.g. a model using solely a character embedding achieves 86% of the performance of the largest model (Elmo, GloVe, Character) while being 1.2% of its size. Second, the larger models using multiple embeddings learns faster despite being slower per epoch. However, it is still slower at test time. Finally, Elmo performs best on both EvCR and EnCR, while GloVe and FastText perform best in EvCR and EnCR respectively.

Most reinforcement learning methods for dialog policy learning train a centralized agent that selects a predefined joint action concatenating domain name, intent type, and slot name. The centralized dialog agent suffers from a great many user-agent interaction requirements due to the large action space. Besides, designing the concatenated actions is laborious to engineers and maybe struggled with edge cases. To solve these problems, we model the dialog policy learning problem with a novel multi-agent framework, in which each part of the action is led by a different agent. The framework reduces labor costs for action templates and decreases the size of the action space for each agent. Furthermore, we relieve the non-stationary problem caused by the changing dynamics of the environment as evolving of agents’ policies by introducing a joint optimization process that makes agents can exchange their policy information. Concurrently, an independent experience replay buffer mechanism is integrated to reduce the dependence between gradients of samples to improve training efficiency. The effectiveness of the proposed framework is demonstrated in a multi-domain environment with both user simulator evaluation and human evaluation.

Pimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion that representations encode exactly the same information about a target task as the original sentences. The mutual information, however, assumes the true probability distribution of a pair of random variables is known, leading to unintuitive results in settings where it is not. This paper proposes a new framework to measure what we term Bayesian mutual information, which analyses information from the perspective of Bayesian agents—allowing for more intuitive findings in scenarios with finite data. For instance, under Bayesian MI we have that data can add information, processing can help, and information can hurt, which makes it more intuitive for machine learning applications. Finally, we apply our framework to probing where we believe Bayesian mutual information naturally operationalises ease of extraction by explicitly limiting the available background knowledge to solve a task.

Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization. In this work, we explore four different challenges of the task: handling and differentiating parts of the dialogue belonging to multiple speakers, negation understanding, reasoning about the situation, and informal language understanding. Using a pretrained sequence-to-sequence language model, we explore speaker name substitution, negation scope highlighting, multi-task learning with relevant tasks, and pretraining on in-domain data. Our experiments show that our proposed techniques indeed improve summarization performance, outperforming strong baselines.

Stance detection, which aims to determine whether an individual is for or against a target concept, promises to uncover public opinion from large streams of social media data. Yet even human annotation of social media content does not always capture “stance” as measured by public opinion polls. We demonstrate this by directly comparing an individual’s self-reported stance to the stance inferred from their social media data. Leveraging a longitudinal public opinion survey with respondent Twitter handles, we conducted this comparison for 1,129 individuals across four salient targets. We find that recall is high for both “Pro’’ and “Anti’’ stance classifications but precision is variable in a number of cases. We identify three factors leading to the disconnect between text and author stance: temporal inconsistencies, differences in constructs, and measurement errors from both survey respondents and annotators. By presenting a framework for assessing the limitations of stance detection models, this work provides important insight into what stance detection truly measures.

Millions of hashtags are created on social media every day to cross-refer messages concerning similar topics. To help people find the topics they want to discuss, this paper characterizes a user’s hashtagging preferences via predicting how likely they will post with a hashtag. It is hypothesized that one’s interests in a hashtag are related with what they said before (user history) and the existing posts present the hashtag (hashtag contexts). These factors are married in the deep semantic space built with a pre-trained BERT and a neural topic model via multitask learning. In this way, user interests learned from the past can be customized to match future hashtags, which is beyond the capability of existing methods assuming unchanged hashtag semantics. Furthermore, we propose a novel personalized topic attention to capture salient contents to personalize hashtag contexts. Experiments on a large-scale Twitter dataset show that our model significantly outperforms the state-of-the-art recommendation approach without exploiting latent topics.